Skip to content
View Dogwind221's full-sized avatar

Block or report Dogwind221

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Dogwind221/README.md

Hi, I'm Dogwind 👋

AI applications, mostly on DeepSeek Harness.

Pinned Loading

  1. img2img-studio img2img-studio Public

    Image-to-image studio: vision-gated routing + multi-provider generation (DashScope / ChatGPT-web / OpenAI / Z.AI / Doubao / MiniMax) with auto failover. E-commerce sets & photo-art styles. 图生图工作台 ·…

    TypeScript 8

  2. dwguard-dsh-hmos dwguard-dsh-hmos Public

    DSH 侧鸿蒙双 Agent 编排与外部审计插件:任务包冻结 / 对抗预审 / Goal 派发 / 四维取证审计 / 返工 / 校准账本

    JavaScript 3

  3. DWcinematic-whitebox DWcinematic-whitebox Public

    DSH skill (DWcinematic-whitebox): script-to-Blender whitebox previz — derives shots, blocking and camera moves, then guides Blender renders in a cinematic style. 剧本转白模预演 · 分镜推导 + 运镜设计

    Python 6

  4. Dw-LiveWorkbench Dw-LiveWorkbench Public

    Zero-dependency AI workbench for livestream content: self-built RAG (BM25 + hashed n-gram vectors, recall@5 0.974), hand-written ReAct agent with 7 tools, multi-tenant RBAC, 372 automated assertion…

    JavaScript 1

  5. dsh-vision-skill dsh-vision-skill Public

    Vision for text-only LLMs: multi-model failover vision API + drag-and-drop image recognition in the DSH web UI. Adapted from claude-vision-skill. 为纯文本模型补视觉能力 · 多模型自动降级

    JavaScript 1